Hybrid quantum physics-informed neural networks for simulating computational fluid dynamics in complex shapes

Abstract

Finding the distribution of the velocities and pressures of a fluid by solving the Navier-Stokes equations is a principal task in the chemical, energy, and pharmaceutical industries, as well as in mechanical engineering and the design of pipeline systems. With existing solvers, such as OpenFOAM and Ansys, simulations of fluid dynamics in intricate geometries are computationally expensive and require re-simulation whenever the geometric parameters or the initial and boundary conditions are altered. Physics-informed neural networks are a promising tool for simulating fluid flows in complex geometries, as they can adapt to changes in the geometry and mesh definitions, allowing for generalization across fluid parameters and transfer learning across different shapes. We present a hybrid quantum physics-informed neural network that simulates laminar fluid flows in 3D Y-shaped mixers. Our approach combines the expressive power of a quantum model with the flexibility of a physics-informed neural network, resulting in a 21% higher accuracy compared to a purely classical neural network. Our findings highlight the potential of machine learning approaches, and in particular hybrid quantum physics-informed neural network, for complex shape optimization tasks in computational fluid dynamics. By improving the accuracy of fluid simulations in complex geometries, our research using hybrid quantum models contributes to the development of more efficient and reliable fluid dynamics solvers.

11 pages, 6 figures

References in corpus (25)

• Fourier Neural Operator for Parametric Partial Differential Equations
• The effect of data encoding on the expressive power of variational quantum machine learning models
• Learning to Simulate Complex Physics with Graph Networks
• Transfer learning in hybrid classical-quantum neural networks
• What is being transferred in transfer learning?
• Solving nonlinear differential equations with differentiable quantum circuits
• Experimental quantum speed-up in reinforcement learning agents
• Quantum machine learning for image classification
• A Quantum Inspired Approach to Exploit Turbulence Structures
• Hybrid quantum neural network for drug response prediction
• Unstructured un-split geometrical Volume-of-Fluid methods -- A review
• Quantum Machine Learning: from physics to software engineering
• Quantum algorithms applied to satellite mission planning for Earth observation
• Quantum Kernel Methods for Solving Differential Equations
• Benchmarking simulated and physical quantum processing units using quantum and hybrid algorithms
• Hybrid quantum ResNet for car classification and its hyperparameter optimization
• Quantum Deep Hedging
• Quantum Machine Learning in Finance: Time Series Forecasting
• Parallel Hybrid Networks: an interplay between quantum and classical neural networks
• Efficient calculation of gradients in classical simulations of variational quantum algorithms
• Practical application-specific advantage through hybrid quantum computing
• An exponentially-growing family of universal quantum circuits
• QDNN: DNN with Quantum Neural Network Layers
• A supervised hybrid quantum machine learning solution to the emergency escape routing problem
• Physics-Informed Quantum Machine Learning: Solving nonlinear differential equations in latent spaces without costly grid evaluations

Cited by in corpus (8)

• Hybrid quantum cycle generative adversarial network for small molecule generation
• A hybrid quantum-classical framework for computational fluid dynamics
• Quantum algorithms for scientific computing
• Forecasting steam mass flow in power plants using the parallel hybrid network
• Fatigue-PINN: Physics-Informed Fatigue-Driven Motion Modulation and Synthesis
• A Hybrid Quantum-Classical Particle-in-Cell Method for Plasma Simulations
• Quantum Physics-Informed Neural Networks for Maxwell's Equations: Circuit Design, "Black Hole" Barren Plateaus Mitigation, and GPU Acceleration
• Discovery of Quasi-Integrable Equations from traveling-wave data using the Physics-Informed Neural Networks